Remove reindexing step from Mistral Large 3 FP8 example#2530
Remove reindexing step from Mistral Large 3 FP8 example#2530omkar-334 wants to merge 3 commits intovllm-project:mainfrom
Conversation
Signed-off-by: Omkar Kabde <omkarkabde@gmail.com>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request refactors the codebase by moving the GPTQModifier from llmcompressor.modifiers.quantization.gptq to llmcompressor.modifiers.gptq. All relevant examples, tests, and documentation have been updated to use the new import path, and a backwards compatibility shim with a deprecation warning has been added to the old location. Furthermore, the Mistral Large 3 FP8 example was updated to remove a weight reindexing step that is no longer required. I have no feedback to provide.
|
👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review. Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed. |
kylesayrs
left a comment
kylesayrs
left a comment
There was a problem hiding this comment.
Could you please update the documentation as well? Thanks!
|
hey @kylesayrs i'm a bit confused, Could you point me to which documentation i need to update? |
2 participants
Fixes #2515
TEST PLAN:
Verify the docs page renders correctly at docs/key-models/mistral-large-3/fp8-example.md
cc @kylesayrs